hengfeiyang commented on code in PR #7821:
URL: https://github.com/apache/arrow-datafusion/pull/7821#discussion_r1366643868
##########
datafusion/core/src/datasource/physical_plan/parquet/row_groups.rs:
##########
@@ -846,4 +1120,185 @@ mod tests {
let execution_props = ExecutionProps::new();
create_physical_expr(expr, &df_schema, schema,
&execution_props).unwrap()
}
+
+ #[tokio::test]
+ async fn test_row_group_bloom_filter_pruning_predicate_simple_expr() {
+ // load parquet file
+ let testdata = datafusion_common::test_util::parquet_test_data();
+ let file_name = "data_index_bloom_encoding_stats.parquet";
+ let path = format!("{testdata}/{file_name}");
+ let data = bytes::Bytes::from(std::fs::read(path).unwrap());
+
+ // generate pruning predicate
+ let schema = Schema::new(vec![Field::new("String", DataType::Utf8,
false)]);
+ let expr = col(r#""String""#).eq(lit("Hello_Not_Exists"));
+ let expr = logical2physical(&expr, &schema);
+ let pruning_predicate =
+ PruningPredicate::try_new(expr, Arc::new(schema)).unwrap();
+
+ let row_groups = vec![0];
+ let pruned_row_groups = test_row_group_bloom_filter_pruning_predicate(
+ file_name,
+ data,
+ &pruning_predicate,
+ &row_groups,
+ )
+ .await
+ .unwrap();
+ assert!(pruned_row_groups.is_empty());
+ }
+
+ #[tokio::test]
+ async fn test_row_group_bloom_filter_pruning_predicate_partial_expr() {
+ // load parquet file
+ let testdata = datafusion_common::test_util::parquet_test_data();
+ let file_name = "data_index_bloom_encoding_stats.parquet";
+ let path = format!("{testdata}/{file_name}");
+ let data = bytes::Bytes::from(std::fs::read(path).unwrap());
+
+ // generate pruning predicate
+ let schema = Schema::new(vec![Field::new("String", DataType::Utf8,
false)]);
+ let expr = col(r#""String""#)
Review Comment:
I deleted `test_row_group_bloom_filter_pruning_predicate_partial_expr`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
